Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2507 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6364. Min Act: -0.0000

Data Index: 343146 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6540. Min Act: -0.0000

Data Index: 32087 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1027953 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6477. Min Act: -0.0000

Data Index: 660735 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6065. Min Act: -0.0000

Data Index: 868572 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5519. Min Act: -0.0000

Data Index: 657231 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5863. Min Act: -0.0000

Data Index: 649632 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5811. Min Act: -0.0000

Data Index: 877307 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1338719 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5850. Min Act: -0.0000

Data Index: 119955 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5502. Min Act: -0.0000

Data Index: 346173 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5630. Min Act: -0.0000

Data Index: 823733 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5426. Min Act: -0.0000

Data Index: 79402 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5243. Min Act: -0.0000

Data Index: 601284 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5363. Min Act: -0.0000

Data Index: 436445 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5064. Min Act: -0.0000

Data Index: 19657 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1155701 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5441. Min Act: -0.0000

Data Index: 527146 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4785. Min Act: -0.0000

Data Index: 973251 (C4 (Web Text))

Max Activating Token Index: 260